暗中两拍：以极少数据采集实现低光照去噪
2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
只需每个 ISO 一张噪声图和一张暗帧即可合成真实噪声，为缺乏配对数据的低光照去噪训练提供了可复用的数据增广方案；其傅里叶域频谱采样生成信号无关噪声的思路，可直接用于构建 RAW 域去噪训练集。
原文依据 we propose a general and practical noise synthesis method that requires only one single noisy image and one single dark frame per ISO setting
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在低光照条件下拍摄的 RAW 图像由于光子数少和传感器噪声而噪声严重。基于学习的去噪器有潜力重建高质量图像。然而在训练时，这些去噪器需要大量干净图像与噪声图像构成的配对数据集，而这类数据难以采集。噪声合成是大规模数据采集的一种替代方案：给定一张干净图像，我们可以合成与之对应的真实感噪声图像。在本工作中，我们提出一种通用且实用的噪声合成方法，对每个 ISO 设置仅需一张噪声图像和一张暗帧。我们用泊松分布表示信号相关噪声，并引入一种傅里叶域频谱采样算法来精确建模信号无关噪声。后者可生成多样化的噪声实现，同时保持真实传感器噪声的空间与统计特性。与同期方法相比，我们的方法既不依赖简化的参数化模型，也不依赖大规模干净-噪声图像对。它准确且实用。此外，我们的合成方法在多个低光照去噪基准上取得了最优的性能。
英文原文摘要 1176 字符
Raw images taken in low-light conditions are very noisy due to low photon count and sensor noise. Learning-based denoisers have the potential to reconstruct high-quality images. For training, however, these denoisers require large paired datasets of clean and noisy images, which are difficult to collect. Noise synthesis is an alternative to large-scale data acquisition: given a clean image, we can synthesize a realistic noisy counterpart. In this work, we propose a general and practical noise synthesis method that requires only one single noisy image and one single dark frame per ISO setting. We represent signal-dependent noise with a Poisson distribution and introduce a Fourier-domain spectral sampling algorithm to accurately model signal-independent noise. The latter generates diverse noise realizations that maintain the spatial and statistical properties of real sensor noise. As opposed to concurrent approaches, our method neither relies on simplified parametric models nor on large sets of clean-noisy image pairs. It is accurate and practical. Moreover, our synthesis method leads to state-of-the-art performances on multiple low-light denoising benchmarks.